Training in progress, step 370

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13e8be25bcca00ffea5792e4838450f65be8391b61a0f034995d38eac82b3076
+oid sha256:852158d1daa73cd8d06116932c299074ae89372e571f5c032cdeb14842dcc804
 size 35668592

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.576,
+  "epoch": 0.592,
   "eval_steps": 20,
-  "global_step": 360,
+  "global_step": 370,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -262,6 +262,21 @@
       "eval_samples_per_second": 3.33,
       "eval_steps_per_second": 0.416,
       "step": 340
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.03991026058793068,
+      "learning_rate": 0.0004493183165382336,
+      "loss": 1.4809,
+      "step": 360
+    },
+    {
+      "epoch": 0.576,
+      "eval_loss": 1.4818130731582642,
+      "eval_runtime": 1501.7616,
+      "eval_samples_per_second": 3.329,
+      "eval_steps_per_second": 0.416,
+      "step": 360
     }
   ],
   "logging_steps": 20,
@@ -281,7 +296,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.81330603188224e+16,
+  "total_flos": 2.892365895794688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null